深度学习: Faster R-CNN 网络

Structure

看不清的可以右键，在新tab中查看该图片：

前部

Faster R-CNN 头部 负责对输入图像进行 特征提取 ：



网络结构有两种，一种是将ZFNet（扔掉了尾端的全连接层）拿来用，另一种则是将VGG拿来用（扔掉了尾端的全连接层）。论文中给出的是第一种（绿框内为拿来用的那部分）：

中部

Faster R-CNN 中部 负责对 特征图 (即前部所提取到的特征) 进行 特征提取 ：



双分支：

绿框内

：【RPN（生成anchor –> 初步的分类及初步的边框回归 –> 洗涤anchor成proposal）】—-》

蓝框内

：【proposal–>RoI】。

红框内

：【特征图的无损传递】。

最后统一交付给

黄框内

：【RoIPooling】 去输出相同size的RoI。

后部

再一次 的 分类任务 和 边框回归任务 来 进一步提升检测精度，并输出检测结果：

Loss Computation

多任务：

Faster R-CNN论文笔记——FR



Fast R-CNN网络有两个同级输出层（cls score和bbox_prdict层），都是全连接层，称为multi-task。

① clsscore层：用于分类，输出k+1维数组p，表示属于k类和背景的概率。对每个RoI（Region of Interesting）输出离散型概率分布



通常，p由k+1类的全连接层利用softmax计算得出。

② bbox_prdict层：用于调整候选区域位置，输出bounding box回归的位移，输出4*K维数组t，表示分别属于k类时，应该平移缩放的参数。



k表示类别的索引，

是指相对于objectproposal尺度不变的平移，

是指对数空间中相对于objectproposal的高与宽。

loss_cls层评估分类损失函数。由真实分类u对应的概率决定：



loss_bbox评估检测框定位的损失函数。比较真实分类对应的预测平移缩放参数

和真实平移缩放参数为


的差别：



其中，smooth L1损失函数为：



smooth L1损失函数曲线如下图9所示，作者这样设置的目的是想让loss对于离群点更加鲁棒，相比于L2损失函数，其对离群点、异常值（outlier）不敏感，可控制梯度的量级使训练时不容易跑飞。



最后总损失为（两者加权和，如果分类为背景则不考虑定位损失）：



规定u=0为背景类（也就是负标签），那么艾弗森括号指数函数[u≥1]表示背景候选区域即负样本不参与回归损失，不需要对候选区域进行回归操作。λ控制分类损失和回归损失的平衡。Fast R-CNN论文中，所有实验λ=1。

艾弗森括号指数函数为：



源码中bbox_loss_weights用于标记每一个bbox是否属于某一个类。

Code

附上作者的源码 rbgirshick/py-faster-rcnn/models/pascal_voc/ZF/faster_rcnn_end2end/train.prototxt ：

name: "ZF"
layer {
name: 'input-data'
type: 'Python'
top: 'data'
top: 'im_info'
top: 'gt_boxes'
python_param {
module: 'roi_data_layer.layer'
layer: 'RoIDataLayer'
param_str: "'num_classes': 21"
}
}

#========= conv1-conv5 ============

layer {
name: "conv1"
type: "Convolution"
bottom: "data"
top: "conv1"
param { lr_mult: 1.0 }
param { lr_mult: 2.0 }
convolution_param {
num_output: 96
kernel_size: 7
pad: 3
stride: 2
}
}
layer {
name: "relu1"
type: "ReLU"
bottom: "conv1"
top: "conv1"
}
layer {
name: "norm1"
type: "LRN"
bottom: "conv1"
top: "norm1"
lrn_param {
local_size: 3
alpha: 0.00005
beta: 0.75
norm_region: WITHIN_CHANNEL
engine: CAFFE
}
}
layer {
name: "pool1"
type: "Pooling"
bottom: "norm1"
top: "pool1"
pooling_param {
kernel_size: 3
stride: 2
pad: 1
pool: MAX
}
}
layer {
name: "conv2"
type: "Convolution"
bottom: "pool1"
top: "conv2"
param { lr_mult: 1.0 }
param { lr_mult: 2.0 }
convolution_param {
num_output: 256
kernel_size: 5
pad: 2
stride: 2
}
}
layer {
name: "relu2"
type: "ReLU"
bottom: "conv2"
top: "conv2"
}
layer {
name: "norm2"
type: "LRN"
bottom: "conv2"
top: "norm2"
lrn_param {
local_size: 3
alpha: 0.00005
beta: 0.75
norm_region: WITHIN_CHANNEL
engine: CAFFE
}
}
layer {
name: "pool2"
type: "Pooling"
bottom: "norm2"
top: "pool2"
pooling_param {
kernel_size: 3
stride: 2
pad: 1
pool: MAX
}
}
layer {
name: "conv3"
type: "Convolution"
bottom: "pool2"
top: "conv3"
param { lr_mult: 1.0 }
param { lr_mult: 2.0 }
convolution_param {
num_output: 384
kernel_size: 3
pad: 1
stride: 1
}
}
layer {
name: "relu3"
type: "ReLU"
bottom: "conv3"
top: "conv3"
}
layer {
name: "conv4"
type: "Convolution"
bottom: "conv3"
top: "conv4"
param { lr_mult: 1.0 }
param { lr_mult: 2.0 }
convolution_param {
num_output: 384
kernel_size: 3
pad: 1
stride: 1
}
}
layer {
name: "relu4"
type: "ReLU"
bottom: "conv4"
top: "conv4"
}
layer {
name: "conv5"
type: "Convolution"
bottom: "conv4"
top: "conv5"
param { lr_mult: 1.0 }
param { lr_mult: 2.0 }
convolution_param {
num_output: 256
kernel_size: 3
pad: 1
stride: 1
}
}
layer {
name: "relu5"
type: "ReLU"
bottom: "conv5"
top: "conv5"
}

#========= RPN ============

layer {
name: "rpn_conv/3x3"
type: "Convolution"
bottom: "conv5"
top: "rpn/output"
param { lr_mult: 1.0 }
param { lr_mult: 2.0 }
convolution_param {
num_output: 256
kernel_size: 3 pad: 1 stride: 1
weight_filler { type: "gaussian" std: 0.01 }
bias_filler { type: "constant" value: 0 }
}
}
layer {
name: "rpn_relu/3x3"
type: "ReLU"
bottom: "rpn/output"
top: "rpn/output"
}

#layer {
#  name: "rpn_conv/3x3"
#  type: "Convolution"
#  bottom: "conv5"
#  top: "rpn_conv/3x3"
#  param { lr_mult: 1.0 }
#  param { lr_mult: 2.0 }
#  convolution_param {
#    num_output: 192
#    kernel_size: 3 pad: 1 stride: 1
#    weight_filler { type: "gaussian" std: 0.01 }
#    bias_filler { type: "constant" value: 0 }
#  }
#}
#layer {
#  name: "rpn_conv/5x5"
#  type: "Convolution"
#  bottom: "conv5"
#  top: "rpn_conv/5x5"
#  param { lr_mult: 1.0 }
#  param { lr_mult: 2.0 }
#  convolution_param {
#    num_output: 64
#    kernel_size: 5 pad: 2 stride: 1
#    weight_filler { type: "gaussian" std: 0.0036 }
#    bias_filler { type: "constant" value: 0 }
#  }
#}
#layer {
#  name: "rpn/output"
#  type: "Concat"
#  bottom: "rpn_conv/3x3"
#  bottom: "rpn_conv/5x5"
#  top: "rpn/output"
#}
#layer {
#  name: "rpn_relu/output"
#  type: "ReLU"
#  bottom: "rpn/output"
#  top: "rpn/output"
#}

layer {
name: "rpn_cls_score"
type: "Convolution"
bottom: "rpn/output"
top: "rpn_cls_score"
param { lr_mult: 1.0 }
param { lr_mult: 2.0 }
convolution_param {
num_output: 18   # 2(bg/fg) * 9(anchors)
kernel_size: 1 pad: 0 stride: 1
weight_filler { type: "gaussian" std: 0.01 }
bias_filler { type: "constant" value: 0 }
}
}
layer {
name: "rpn_bbox_pred"
type: "Convolution"
bottom: "rpn/output"
top: "rpn_bbox_pred"
param { lr_mult: 1.0 }
param { lr_mult: 2.0 }
convolution_param {
num_output: 36   # 4 * 9(anchors)
kernel_size: 1 pad: 0 stride: 1
weight_filler { type: "gaussian" std: 0.01 }
bias_filler { type: "constant" value: 0 }
}
}
layer {
bottom: "rpn_cls_score"
top: "rpn_cls_score_reshape"
name: "rpn_cls_score_reshape"
type: "Reshape"
reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }
}
layer {
name: 'rpn-data'
type: 'Python'
bottom: 'rpn_cls_score'
bottom: 'gt_boxes'
bottom: 'im_info'
bottom: 'data'
top: 'rpn_labels'
top: 'rpn_bbox_targets'
top: 'rpn_bbox_inside_weights'
top: 'rpn_bbox_outside_weights'
python_param {
module: 'rpn.anchor_target_layer'
layer: 'AnchorTargetLayer'
param_str: "'feat_stride': 16"
}
}
layer {
name: "rpn_loss_cls"
type: "SoftmaxWithLoss"
bottom: "rpn_cls_score_reshape"
bottom: "rpn_labels"
propagate_down: 1
propagate_down: 0
top: "rpn_cls_loss"
loss_weight: 1
loss_param {
ignore_label: -1
normalize: true
}
}
layer {
name: "rpn_loss_bbox"
type: "SmoothL1Loss"
bottom: "rpn_bbox_pred"
bottom: "rpn_bbox_targets"
bottom: 'rpn_bbox_inside_weights'
bottom: 'rpn_bbox_outside_weights'
top: "rpn_loss_bbox"
loss_weight: 1
smooth_l1_loss_param { sigma: 3.0 }
}

#========= RoI Proposal ============

layer {
name: "rpn_cls_prob"
type: "Softmax"
bottom: "rpn_cls_score_reshape"
top: "rpn_cls_prob"
}
layer {
name: 'rpn_cls_prob_reshape'
type: 'Reshape'
bottom: 'rpn_cls_prob'
top: 'rpn_cls_prob_reshape'
reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }
}
layer {
name: 'proposal'
type: 'Python'
bottom: 'rpn_cls_prob_reshape'
bottom: 'rpn_bbox_pred'
bottom: 'im_info'
top: 'rpn_rois'
#  top: 'rpn_scores'
python_param {
module: 'rpn.proposal_layer'
layer: 'ProposalLayer'
param_str: "'feat_stride': 16"
}
}
#layer {
#  name: 'debug-data'
#  type: 'Python'
#  bottom: 'data'
#  bottom: 'rpn_rois'
#  bottom: 'rpn_scores'
#  python_param {
#    module: 'rpn.debug_layer'
#    layer: 'RPNDebugLayer'
#  }
#}
layer {
name: 'roi-data'
type: 'Python'
bottom: 'rpn_rois'
bottom: 'gt_boxes'
top: 'rois'
top: 'labels'
top: 'bbox_targets'
top: 'bbox_inside_weights'
top: 'bbox_outside_weights'
python_param {
module: 'rpn.proposal_target_layer'
layer: 'ProposalTargetLayer'
param_str: "'num_classes': 21"
}
}

#========= RCNN ============

layer {
name: "roi_pool_conv5"
type: "ROIPooling"
bottom: "conv5"
bottom: "rois"
top: "roi_pool_conv5"
roi_pooling_param {
pooled_w: 6
pooled_h: 6
spatial_scale: 0.0625 # 1/16
}
}
layer {
name: "fc6"
type: "InnerProduct"
bottom: "roi_pool_conv5"
top: "fc6"
param { lr_mult: 1.0 }
param { lr_mult: 2.0 }
inner_product_param {
num_output: 4096
}
}
layer {
name: "relu6"
type: "ReLU"
bottom: "fc6"
top: "fc6"
}
layer {
name: "drop6"
type: "Dropout"
bottom: "fc6"
top: "fc6"
dropout_param {
dropout_ratio: 0.5
scale_train: false
}
}
layer {
name: "fc7"
type: "InnerProduct"
bottom: "fc6"
top: "fc7"
param { lr_mult: 1.0 }
param { lr_mult: 2.0 }
inner_product_param {
num_output: 4096
}
}
layer {
name: "relu7"
type: "ReLU"
bottom: "fc7"
top: "fc7"
}
layer {
name: "drop7"
type: "Dropout"
bottom: "fc7"
top: "fc7"
dropout_param {
dropout_ratio: 0.5
scale_train: false
}
}
layer {
name: "cls_score"
type: "InnerProduct"
bottom: "fc7"
top: "cls_score"
param { lr_mult: 1.0 }
param { lr_mult: 2.0 }
inner_product_param {
num_output: 21
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bbox_pred"
type: "InnerProduct"
bottom: "fc7"
top: "bbox_pred"
param { lr_mult: 1.0 }
param { lr_mult: 2.0 }
inner_product_param {
num_output: 84
weight_filler {
type: "gaussian"
std: 0.001
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "loss_cls"
type: "SoftmaxWithLoss"
bottom: "cls_score"
bottom: "labels"
propagate_down: 1
propagate_down: 0
top: "cls_loss"
loss_weight: 1
loss_param {
ignore_label: -1
normalize: true
}
}
layer {
name: "loss_bbox"
type: "SmoothL1Loss"
bottom: "bbox_pred"
bottom: "bbox_targets"
bottom: 'bbox_inside_weights'
bottom: 'bbox_outside_weights'
top: "bbox_loss"
loss_weight: 1
}